Feature extraction for speech and music discrimination.
Huiyu ZhouAbdul Hamid SadkaRichard M. JiangPublished in: CBMI (2008)
Keyphrases
- feature extraction
- audio signals
- speech music discrimination
- speaker identification
- feature selection
- audio features
- audio recordings
- speech recognition
- digital audio
- preprocessing
- automatic speech recognition
- audio signal
- speech signal
- pattern classification
- cepstral features
- feature set
- music information retrieval
- face recognition
- mel frequency cepstral coefficients
- image classification
- endpoint detection
- spoken language
- image processing
- feature extraction and classification
- feature space
- audio visual
- discriminant analysis
- computer music
- principal component analysis
- music retrieval
- feature extractor
- dimensionality reduction
- speech synthesis
- acoustic features
- support vector machine svm
- feature extractors
- feature vectors
- texture features
- music recommendation
- recognition engine
- dimension reduction
- wavelet transform
- linear predictive
- pattern recognition
- broadcast news
- linear feature extraction
- speaker recognition
- hidden markov models
- extracting features
- correlation filters
- low level
- noisy environments
- extracted features
- texture analysis
- linear discriminant analysis
- gaussian mixture model
- non stationary
- multi modal